Skip to content

Instantly share code, notes, and snippets.

@zyocum

zyocum/example.txt

Created February 21, 2020 19:50
Show Gist options
  • Save zyocum/c20ab48c82dd20ac02766b8b7c1598cb to your computer and use it in GitHub Desktop.
Save zyocum/c20ab48c82dd20ac02766b8b7c1598cb to your computer and use it in GitHub Desktop.
Download ZIP
Raw
example.txt
$ curl -sX POST -H "X-RosetteAPI-Key: $ROSETTE_USER_KEY" -H "Content-Type: application/json" -H "Accept: application/json" -d '{"content":"Salesforce.com, Inc. is an American cloud-based software company headquartered in San Francisco."}' 'https://api.rosette.com/rest/v1/entities?output=rosette' | jq .
{
"version": "1.1.0",
"data": "Salesforce.com, Inc. is an American cloud-based software company headquartered in San Francisco.",
"attributes": {
"scriptRegion": {
"type": "list",
"itemType": "scriptRegion",
"items": [
{
"startOffset": 0,
"endOffset": 96,
"script": "Latn"
}
]
},
"sentence": {
"type": "list",
"itemType": "sentence",
"items": [
{
"startOffset": 0,
"endOffset": 96
}
]
},
"languageDetection": {
"type": "languageDetection",
"startOffset": 0,
"endOffset": 96,
"detectionResults": [
{
"language": "eng",
"encoding": "UTF-16BE",
"script": "Latn",
"confidence": 0.92100834
}
]
},
"token": {
"type": "list",
"itemType": "token",
"items": [
{
"startOffset": 0,
"endOffset": 14,
"text": "Salesforce.com",
"analyses": [
{
"partOfSpeech": "URL",
"lemma": "Salesforce.com",
"tagSet": "BT_LANGUAGE_NEUTRAL"
},
{
"partOfSpeech": "ADJ",
"lemma": "Salesforce.com",
"raw": "Salesforce.com[+ADJ]",
"tagSet": "BT_ENGLISH"
},
{
"partOfSpeech": "NOUN",
"lemma": "Salesforce.com",
"raw": "Salesforce.com[+NOUN]",
"tagSet": "BT_ENGLISH"
},
{
"partOfSpeech": "PROP",
"lemma": "Salesforce.com",
"raw": "Salesforce.com[+PROP]",
"tagSet": "BT_ENGLISH"
}
]
},
{
"startOffset": 14,
"endOffset": 15,
"text": ",",
"analyses": [
{
"partOfSpeech": "CM",
"lemma": ",",
"raw": ",[+CM]",
"tagSet": "BT_ENGLISH"
}
]
},
{
"startOffset": 16,
"endOffset": 20,
"text": "Inc.",
"analyses": [
{
"partOfSpeech": "PROP",
"lemma": "Inc.",
"raw": "Inc.[+Prop][+PROP]",
"tagSet": "BT_ENGLISH"
},
{
"partOfSpeech": "NOUN",
"lemma": "inc.",
"raw": "inc.[+NOUN]",
"tagSet": "BT_ENGLISH"
}
]
},
{
"startOffset": 21,
"endOffset": 23,
"text": "is",
"analyses": [
{
"partOfSpeech": "VBPRES",
"lemma": "be",
"raw": "be[+VBPRES]",
"tagSet": "BT_ENGLISH"
}
]
},
{
"startOffset": 24,
"endOffset": 26,
"text": "an",
"analyses": [
{
"partOfSpeech": "DET",
"lemma": "an",
"raw": "an[+DET]",
"tagSet": "BT_ENGLISH"
}
]
},
{
"startOffset": 27,
"endOffset": 35,
"text": "American",
"analyses": [
{
"partOfSpeech": "ADJ",
"lemma": "American",
"raw": "American[+ADJ]",
"tagSet": "BT_ENGLISH"
},
{
"partOfSpeech": "NOUN",
"lemma": "American",
"raw": "American[+NOUN]",
"tagSet": "BT_ENGLISH"
}
]
},
{
"startOffset": 36,
"endOffset": 41,
"text": "cloud",
"analyses": [
{
"partOfSpeech": "NOUN",
"lemma": "cloud",
"raw": "cloud[+NOUN]",
"tagSet": "BT_ENGLISH"
},
{
"partOfSpeech": "VI",
"lemma": "cloud",
"raw": "cloud[+VI]",
"tagSet": "BT_ENGLISH"
},
{
"partOfSpeech": "VPRES",
"lemma": "cloud",
"raw": "cloud[+VPRES]",
"tagSet": "BT_ENGLISH"
}
]
},
{
"startOffset": 41,
"endOffset": 42,
"text": "-",
"analyses": [
{
"partOfSpeech": "PUNCT",
"lemma": "-",
"raw": "-[+PUNCT]",
"tagSet": "BT_ENGLISH"
}
]
},
{
"startOffset": 42,
"endOffset": 47,
"text": "based",
"analyses": [
{
"partOfSpeech": "VPAP",
"lemma": "base",
"raw": "base[+VPAP]",
"tagSet": "BT_ENGLISH"
},
{
"partOfSpeech": "ADJPAP",
"lemma": "based",
"raw": "based[+ADJPAP]",
"tagSet": "BT_ENGLISH"
},
{
"partOfSpeech": "VPAST",
"lemma": "base",
"raw": "base[+VPAST]",
"tagSet": "BT_ENGLISH"
},
{
"partOfSpeech": "PARTPAST",
"lemma": "base",
"raw": "base[+PARTPAST]",
"tagSet": "BT_ENGLISH"
}
]
},
{
"startOffset": 48,
"endOffset": 56,
"text": "software",
"analyses": [
{
"partOfSpeech": "NOUN",
"lemma": "software",
"raw": "software[+NOUN]",
"tagSet": "BT_ENGLISH"
}
]
},
{
"startOffset": 57,
"endOffset": 64,
"text": "company",
"analyses": [
{
"partOfSpeech": "NOUN",
"lemma": "company",
"raw": "company[+NOUN]",
"tagSet": "BT_ENGLISH"
}
]
},
{
"startOffset": 65,
"endOffset": 78,
"text": "headquartered",
"analyses": [
{
"partOfSpeech": "VPAP",
"lemma": "headquarter",
"raw": "headquarter[+VPAP]",
"tagSet": "BT_ENGLISH"
},
{
"partOfSpeech": "ADJPAP",
"lemma": "headquartered",
"raw": "headquartered[+ADJPAP]",
"tagSet": "BT_ENGLISH"
},
{
"partOfSpeech": "VPAST",
"lemma": "headquarter",
"raw": "headquarter[+VPAST]",
"tagSet": "BT_ENGLISH"
},
{
"partOfSpeech": "PARTPAST",
"lemma": "headquarter",
"raw": "headquarter[+PARTPAST]",
"tagSet": "BT_ENGLISH"
}
]
},
{
"startOffset": 79,
"endOffset": 81,
"text": "in",
"analyses": [
{
"partOfSpeech": "PREP",
"lemma": "in",
"raw": "in[+PREP]",
"tagSet": "BT_ENGLISH"
},
{
"partOfSpeech": "ADJ",
"lemma": "in",
"raw": "in[+ADJ]",
"tagSet": "BT_ENGLISH"
},
{
"partOfSpeech": "ADV",
"lemma": "in",
"raw": "in[+ADV]",
"tagSet": "BT_ENGLISH"
},
{
"partOfSpeech": "NOUN",
"lemma": "in",
"raw": "in[+NOUN]",
"tagSet": "BT_ENGLISH"
}
]
},
{
"startOffset": 82,
"endOffset": 85,
"text": "San",
"analyses": [
{
"partOfSpeech": "PROP",
"lemma": "San",
"raw": "San[+Prop][+PROP]",
"tagSet": "BT_ENGLISH"
}
]
},
{
"startOffset": 86,
"endOffset": 95,
"text": "Francisco",
"analyses": [
{
"partOfSpeech": "PROP",
"lemma": "Francisco",
"raw": "Francisco[+Prop][+Masc][+PROP]",
"tagSet": "BT_ENGLISH"
},
{
"partOfSpeech": "PROP",
"lemma": "Francisco",
"raw": "Francisco[+Prop][+Misc][+PROP]",
"tagSet": "BT_ENGLISH"
}
]
},
{
"startOffset": 95,
"endOffset": 96,
"text": ".",
"analyses": [
{
"partOfSpeech": "SENT",
"lemma": ".",
"raw": ".[+SENT]",
"tagSet": "BT_ENGLISH"
}
]
}
]
},
"entities": {
"type": "list",
"itemType": "entities",
"items": [
{
"mentions": [
{
"startOffset": 0,
"endOffset": 20,
"confidence": 0.79843867,
"linkingConfidence": 0.69405192,
"source": "statistical",
"subsource": "/ephemeral/rosapi/roots/rex/7.44.1.c62.2/data/statistical/eng/model-LE.bin",
"normalized": "Salesforce.com"
}
],
"headMentionIndex": 0,
"type": "ORGANIZATION",
"entityId": "Q941127"
},
{
"mentions": [
{
"startOffset": 27,
"endOffset": 35,
"source": "gazetteer",
"subsource": "/data/roots//rex/7.44.1.c62.2/data/gazetteer/eng/accept/gaz-LE.bin",
"normalized": "American"
}
],
"headMentionIndex": 0,
"type": "NATIONALITY",
"entityId": "T1"
},
{
"mentions": [
{
"startOffset": 82,
"endOffset": 95,
"linkingConfidence": 0.68758218,
"source": "gazetteer",
"subsource": "/data/roots//rex/7.44.1.c62.2/data/gazetteer/eng/accept/gaz-LE.bin",
"normalized": "San Francisco"
}
],
"headMentionIndex": 0,
"type": "LOCATION",
"entityId": "Q62"
}
]
}
},
"documentMetadata": {
"processedBy": [
"[email protected]",
"[email protected]"
]
}
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment